The MASQuant code is difficult to use

Thank you for proposing such an insightful work! However, when I tried to run the MASQuant code, I encountered several issues:

1. The conda environment is very difficult to configure. It would be helpful if the exact versions of the dependency packages could be clearly specified.

2. The codebase appears somewhat messy, and there seems to be a lot of code that is unrelated to multimodal models.

3. In the provided examples, I did not find any logic related to the use of LoRA, which seems inconsistent with the description in the paper.

4. Regarding the actual inference speed, it seems that the CUDA kernel implementation has not been provided.

Start by inspecting the conda environment configuration and provided examples, then compare the documented LoRA usage with the paper and check whether the CUDA kernel implementation is present. The issue bundles dependency pinning, code cleanup, LoRA examples, and kernel work; split these into actionable tasks and define completion criteria for each.

Written by the indexing model from the issue text.